pr-status-review
Pass
Audited by Gen Agent Trust Hub on Aug 1, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill exclusively uses the official GitHub CLI (
gh) to interact with GitHub's API. All operations are limited to reading data (listing PRs, checking CI status, and viewing reviews) authored by the current user. There are no hardcoded credentials, unauthorized network calls, or persistence mechanisms detected. - [PROMPT_INJECTION]: The skill processes untrusted data from GitHub pull requests, creating an indirect prompt injection attack surface where malicious content in PR metadata could attempt to influence the agent's summary or recommendations.
- Ingestion points: The agent retrieves potentially attacker-controlled content (PR titles, comments, and review threads) via
gh search prs,gh pr view, andgh api graphqlcommands (SKILL.md). - Boundary markers: The instructions do not define explicit delimiters or instructions to ignore embedded commands within the fetched PR data.
- Capability inventory: The skill's primary capabilities include executing shell commands via the GitHub CLI and formatting data into tables.
- Sanitization: No specific sanitization or filtering steps are provided to handle the content of PR titles or review comments before they are processed by the agent.
Audit Metadata